Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Conference

Face pose reconstruction based on multitask detail compensated generative adversarial networks

Shasha Wu Hualong Zhang Tianci Liu Zhiye Xu
Jul 2026 · International Conference on Machine Vision, Automatic Identification and Detection · Vol 14261, pp. 142610L - 142610L-6 · 0 citations · 7 references
Engineering

TL;DR

A Multitask Detail Compensated Generative Adversarial Networks (MDC-GAN) is proposed, which improves the effect of generating face details and preserving identity through multi-task learning and multi-scale feature fusion.

Abstract

Face pose variation is easy to cause feature loss and face recognition rate decline, which is a key problem in the field of face image generation and recognition. Existing face generation methods based on encoder-decoder often focus on pose conversion and lose facial detail features. This paper proposes a Multitask Detail Compensated Generative Adversarial Networks (MDC-GAN), which improves the effect of generating face details and preserving identity through multi-task learning and multi-scale feature fusion. It has achieved good face reconstruction results on the FERET database, and the results are better than other current methods.

DOI Semantic Scholar
View source

Similar papers

2026

DiEL: Disentangled Evolutionary Learning for Identity-Preserving Face Enhancement and Recognition

The purpose of face enhancement tasks is to improve the recognition of faces, thus adapting to diverse visualization and recognition demands. However, the performance of the majority methods is drastically degraded under extreme conditions, including large pose variations, low resolution, blur, occlusion, and illuminat...

Jing-Wei Xin, Tian Yang, Jun Hao et al. · 0 citations
Open access 2026

Mitigating Adversarial Vulnerabilities in Deep Learning-Based Face Recognition Using Stacked Attention Residual GAN and Fire Hawk Optimization

Optimize Deep Learning–based Adversarial Defense Mechanism (ODL-ADM) is proposed in this work, which projects adversarial samples into an immune feature space that is both discriminative and resistant to perturbations.

Sheilla Ann Bangoy Pacheco, Mahesh Goyani, Jayzel P. Bangoy et al. · 0 citations
Open access Aug 2026

Facial recognition utilizing the SqueezeNet deep learning model

This endeavor uses Transfer Learning to improve the performance of face-recognition systems, particularly when working with a limited dataset, and a pre-trained model known as Squeeznet CNN in MATLAB is employed.

Hussein A. Hussein Al-Delfi · 0 citations
Open access Aug 2026

PixelBoost 8 – Pixel Quality with 8X Highlights Boosting Enhancement

This work proposes a new GAN-based face hallucination method primarily based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN), and presents a personalised adaptation of ESRGAN that employs the VGG16 architecture with a compact pre-trained version.

Sheetal S. Patil, A. Pawar, Nilofar Mulla et al. · 0 citations
Conference Open access 2026

Deepfake Face Detection from GAN to Diffusion Model

Analysis of image-level face forgery detection from three perspectives shows that cross-domain performance is closely related to the physical universality of the detection cues, and methods based on physical constraints exhibit more stable generalization capabilities.

Han-Yao Xu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.